© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10674
    Prev
    Next
    INDEX
    Explanations

    system classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    主è¦ģæĺ¯æĮĩ
    -0.08
     itself
    -0.08
    ByID
    -0.07
    pip
    -0.07
    eia
    -0.07
    otle
    -0.07
    ossi
    -0.07
     irgendwie
    -0.07
    åĴĮçī¹çĤ¹
    -0.07
    onter
    -0.07
    POSITIVE LOGITS
    æ³ķçŃī
    0.08
    æ³ķ
    0.08
     Kort
    0.08
     approach
    0.07
    满天
    0.07
    çŃīæĸ°
    0.06
     zufolge
    0.06
    à¹ĭว
    0.06
    ®
    0.06
    å¨ĺ
    0.06
    Activations Density 0.039%

    No Known Activations